June 23, 2009
CUDA, Supercomputing for the Masses: Part 13Conclusion
This installment presents some straightforward examples that demonstrate the use of texture objects with CUDA. As discussed, texture memory provides many more capabilities aside from those demonstrated in the reverseArray_multiblockTexture.cu example. Please look to the example codes in the NVIDIA_CUDA_SDK projects folder for more complicated examples. The Internet also contains many more useful examples as well that you can download and try. Following are two possibilities:
An excellent resource to learn more about the texture cache and other methods for data reuse on GPUs is Mark Silberstein's paper Efficient Computation of Sum-products on GPUs Through Software Managed Cache. As suggested at the beginning of this article, the paper by Govindaraju and Manocha, Cache-Efficient Numerical Algorithms using Graphics Hardware is also an excellent resource. For a more mathematically oriented view towards textures and caches, check out http://www.cs.lth.se/EDA075/notes/mgh_ch5.pdf.
For More Information
Previous Page |
1 Introduction
|
2 Linear Memory
|
3 An Example
|
4 Conclusion
|
 |
|
|||||||||||||||||||||||||||||
|
|
|
